Agentic Checkout in Chat: Stripe ACP and Shopify in 2026
Stripe and OpenAI shipped the Agentic Commerce Protocol in 2026 with Shared Payment Tokens. Here is what an in-chat agentic checkout actually looks like in production.
11 min read
Agentic AI & LLMs
Agentic AI & LLMs archive page 340 of 631
Agentic AI & LLMs
Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Latest articles
SRTP Key Exchange for HIPAA in 2026: DTLS-SRTP, SDES, and the Bridge Between Them
SDES + TLS works for SIP trunks; DTLS-SRTP wins for WebRTC. For HIPAA-bound AI voice that crosses both worlds, the SBC is where the translation happens. Here is the 2026 reality.
11 min read
WebRTC SDP Munging: When AI Voice Agents Actually Need It (2026)
SDP munging is a footgun. But for AI voice agents it is sometimes the only way to control codecs, strip private candidates, or pin Opus DTX. Here is the 2026 playbook.
10 min
Replace PolyAI With a Multi-Agent OpenAI Agents SDK Stack
PolyAI's Agent Studio is great for enterprise but pricing is bespoke and customization is gated. Build the same containment with the OpenAI Agents SDK in 400 lines.
13 min read
Chat for Role and Permission Changes: SCIM-Aware Patterns for B2B SaaS in 2026
SCIM is now treating AI agents themselves as identities; the same plumbing should let your chat agent change human roles and permissions safely. Here is how to wire SCIM into chat without breaking your IAM model.
10 min read
iOS Audio Session Config for AI Voice (2026): Interruption Handling Done Right
AVAudioSession is the make-or-break for AI voice agents on iOS. Here is the 2026 production playbook for category, mode, options, and interruption recovery.
11 min
Logging and Monitoring for HIPAA Security Incidents in AI Voice Platforms
Audit logs at 45 CFR 164.312(b) plus security monitoring at 45 CFR 164.308(a)(1)(ii)(D) plus 60-day breach clocks. Here is the 2026 logging and SOC architecture for AI voice platforms.
11 min read
mcp-puppeteer vs Playwright MCP in 2026: The Browsing Agent Stack
The official puppeteer MCP went unmaintained; the MCP team recommends Playwright. We compare both, look at withLinda/puppeteer-real-browser-mcp-server for stealth, and show the browsing-agent loop.
10 min read
Conversational NPS and CSAT: Why Chat Surveys Hit 44% Response Rates
Conversational surveys reach 44% response rates versus 10-15% for traditional methods. Here is how to collect NPS and CSAT through chat without the survey fatigue that kills your data quality.
9 min read